AutoML Leaderboard

Best model	name	model_type	metric_type	metric_value	train_time
	1_Baseline	Baseline	logloss	0.659979	1.55
	2_DecisionTree	Decision Tree	logloss	1.7814	12.65
	3_Linear	Linear	logloss	0.499367	4.8
	4_Default_Xgboost	Xgboost	logloss	0.57594	6.77
	5_Default_NeuralNetwork	Neural Network	logloss	0.500703	2.55
	6_Default_RandomForest	Random Forest	logloss	0.426778	8.32
the best	Ensemble	Ensemble	logloss	0.415842	0.44

AutoML Performance

AutoML Performance Boxplot

Features Importance

features importance across models

Spearman Correlation of Models

models spearman correlation

Summary of 6_Default_RandomForest

<< Go back

Random Forest

n_jobs: -1
criterion: gini
max_features: 0.9
min_samples_split: 30
max_depth: 4
eval_metric_name: logloss
explain_level: 2

Validation

validation_type: split
train_ratio: 0.75
shuffle: True
stratify: True

Optimized metric

logloss

Training time

6.9 seconds

Metric details

	score	threshold
logloss	0.426778	nan
auc	0.833333	nan
f1	0.8	0.333481
accuracy	0.842105	0.333481
precision	1	0.607837
recall	1	0.160236
mcc	0.676123	0.607837

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.426778	nan
auc	0.833333	nan
f1	0.8	0.333481
accuracy	0.842105	0.333481
precision	0.75	0.333481
recall	0.857143	0.333481
mcc	0.674601	0.333481

Confusion matrix (at threshold=0.333481)

	Predicted as No	Predicted as Yes
Labeled as No	10	2
Labeled as Yes	1	6

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

SHAP Dependence plots

Dependence (Fold 1)

SHAP Dependence from Fold 1

SHAP Decision plots

Top-10 Worst decisions for class 0 (Fold 1)

SHAP worst decisions class 0 from Fold 1

Top-10 Best decisions for class 0 (Fold 1)

SHAP best decisions class 0 from Fold 1

Top-10 Worst decisions for class 1 (Fold 1)

SHAP worst decisions class 1 from Fold 1

Top-10 Best decisions for class 1 (Fold 1)

SHAP best decisions class 1 from Fold 1

<< Go back

Summary of 2_DecisionTree

<< Go back

Decision Tree

n_jobs: -1
criterion: gini
max_depth: 3
explain_level: 2

Validation

validation_type: split
train_ratio: 0.75
shuffle: True
stratify: True

Optimized metric

logloss

Training time

11.2 seconds

Metric details

	score	threshold
logloss	1.7814	nan
auc	0.660714	nan
f1	0.727273	0.37931
accuracy	0.842105	0.37931
precision	1	0.37931
recall	0.714286	0
mcc	0.676123	0.37931

Metric details with threshold from accuracy metric

	score	threshold
logloss	1.7814	nan
auc	0.660714	nan
f1	0.727273	0.37931
accuracy	0.842105	0.37931
precision	1	0.37931
recall	0.571429	0.37931
mcc	0.676123	0.37931

Confusion matrix (at threshold=0.37931)

	Predicted as No	Predicted as Yes
Labeled as No	12	0
Labeled as Yes	3	4

Learning curves

Decision Tree

Tree #1

Rules

if (Marital status <= 0.5) and (Your current year of Study <= 3.5) and (Your current year of Study > 1.5) then class: No (proba: 62.07%) | based on 29 samples

if (Marital status <= 0.5) and (Your current year of Study > 3.5) then class: No (proba: 100.0%) | based on 12 samples

if (Marital status > 0.5) then class: Yes (proba: 100.0%) | based on 8 samples

if (Marital status <= 0.5) and (Your current year of Study <= 3.5) and (Your current year of Study <= 1.5) then class: No (proba: 100.0%) | based on 7 samples

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

SHAP Dependence plots

Dependence (Fold 1)

SHAP Dependence from Fold 1

SHAP Decision plots

Top-10 Worst decisions for class 0 (Fold 1)

SHAP worst decisions class 0 from Fold 1

Top-10 Best decisions for class 0 (Fold 1)

SHAP best decisions class 0 from Fold 1

Top-10 Worst decisions for class 1 (Fold 1)

SHAP worst decisions class 1 from Fold 1

Top-10 Best decisions for class 1 (Fold 1)

SHAP best decisions class 1 from Fold 1

<< Go back

Summary of 5_Default_NeuralNetwork

<< Go back

Neural Network

n_jobs: -1
dense_1_size: 32
dense_2_size: 16
learning_rate: 0.05
explain_level: 2

Validation

validation_type: split
train_ratio: 0.75
shuffle: True
stratify: True

Optimized metric

logloss

Training time

1.3 seconds

Metric details

	score	threshold
logloss	0.500703	nan
auc	0.785714	nan
f1	0.769231	0.310576
accuracy	0.842105	0.382559
precision	1	0.382559
recall	1	0.0539663
mcc	0.676123	0.382559

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.500703	nan
auc	0.785714	nan
f1	0.727273	0.382559
accuracy	0.842105	0.382559
precision	1	0.382559
recall	0.571429	0.382559
mcc	0.676123	0.382559

Confusion matrix (at threshold=0.382559)

	Predicted as No	Predicted as Yes
Labeled as No	12	0
Labeled as Yes	3	4

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 4_Default_Xgboost

<< Go back

Extreme Gradient Boosting (Xgboost)

n_jobs: -1
objective: binary:logistic
eta: 0.075
max_depth: 6
min_child_weight: 1
subsample: 1.0
colsample_bytree: 1.0
eval_metric: logloss
explain_level: 2

Validation

validation_type: split
train_ratio: 0.75
shuffle: True
stratify: True

Optimized metric

logloss

Training time

5.1 seconds

Metric details

	score	threshold
logloss	0.57594	nan
auc	0.761905	nan
f1	0.833333	0.59002
accuracy	0.894737	0.59002
precision	1	0.59002
recall	1	0.137095
mcc	0.782461	0.59002

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.57594	nan
auc	0.761905	nan
f1	0.833333	0.59002
accuracy	0.894737	0.59002
precision	1	0.59002
recall	0.714286	0.59002
mcc	0.782461	0.59002

Confusion matrix (at threshold=0.59002)

	Predicted as No	Predicted as Yes
Labeled as No	12	0
Labeled as Yes	2	5

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

SHAP Dependence plots

Dependence (Fold 1)

SHAP Dependence from Fold 1

SHAP Decision plots

Top-10 Worst decisions for class 0 (Fold 1)

SHAP worst decisions class 0 from Fold 1

Top-10 Best decisions for class 0 (Fold 1)

SHAP best decisions class 0 from Fold 1

Top-10 Worst decisions for class 1 (Fold 1)

SHAP worst decisions class 1 from Fold 1

Top-10 Best decisions for class 1 (Fold 1)

SHAP best decisions class 1 from Fold 1

<< Go back

Summary of 1_Baseline

<< Go back

Baseline Classifier (Baseline)

n_jobs: -1
explain_level: 2

Validation

validation_type: split
train_ratio: 0.75
shuffle: True
stratify: True

Optimized metric

logloss

Training time

0.5 seconds

Metric details

	score	threshold
logloss	0.659979	nan
auc	0.5	nan
f1	0.538462	0.305357
accuracy	0.368421	0.305357
precision	0.368421	0.305357
recall	1	0.305357
mcc	0	0.305357

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.659979	nan
auc	0.5	nan
f1	0.538462	0.305357
accuracy	0.368421	0.305357
precision	0.368421	0.305357
recall	1	0.305357
mcc	0	0.305357

Confusion matrix (at threshold=0.305357)

	Predicted as No	Predicted as Yes
Labeled as No	0	12
Labeled as Yes	0	7

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of Ensemble

<< Go back

Ensemble structure

Model	Weight
3_Linear	1
6_Default_RandomForest	2

Metric details

	score	threshold
logloss	0.415842	nan
auc	0.809524	nan
f1	0.833333	0.382845
accuracy	0.894737	0.382845
precision	1	0.382845
recall	1	0.112398
mcc	0.782461	0.382845

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.415842	nan
auc	0.809524	nan
f1	0.833333	0.382845
accuracy	0.894737	0.382845
precision	1	0.382845
recall	0.714286	0.382845
mcc	0.782461	0.382845

Confusion matrix (at threshold=0.382845)

	Predicted as No	Predicted as Yes
Labeled as No	12	0
Labeled as Yes	2	5

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 3_Linear

<< Go back

Logistic Regression (Linear)

n_jobs: -1
explain_level: 2

Validation

validation_type: split
train_ratio: 0.75
shuffle: True
stratify: True

Optimized metric

logloss

Training time

3.4 seconds

Metric details

	score	threshold
logloss	0.499367	nan
auc	0.77381	nan
f1	0.833333	0.573201
accuracy	0.894737	0.573201
precision	1	0.573201
recall	1	0.0167229
mcc	0.782461	0.573201

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.499367	nan
auc	0.77381	nan
f1	0.833333	0.573201
accuracy	0.894737	0.573201
precision	1	0.573201
recall	0.714286	0.573201
mcc	0.782461	0.573201

Confusion matrix (at threshold=0.573201)

	Predicted as No	Predicted as Yes
Labeled as No	12	0
Labeled as Yes	2	5

Learning curves

Coefficients

feature	Learner_1
Marital status	1.49327
Did you seek any specialist for a treatment?	0.646115
Do you have Anxiety?	0.539524
age	0.354082
Do you have Panic attack?	0.267781
Your current year of Study	0.0854077
Timestamp	0.0640348
What is your course?	0.0580102
What is your CGPA?	-0.326016
intercept	-0.723588
Choose your gender	-0.755524